Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

Changes of note:

 1) Allow to schedule ICMP packets in IPVS, from Alex Gartrell.

 2) Provide FIB table ID in ipv4 route dumps just as ipv6 does, from
    David Ahern.

 3) Allow the user to ask for the statistics to be filtered out of
    ipv4/ipv6 address netlink dumps.  From Sowmini Varadhan.

 4) More work to pass the network namespace context around deep into
    various packet path APIs, starting with the netfilter hooks.  From
    Eric W Biederman.

 5) Add layer 2 TX/RX checksum offloading to qeth driver, from Thomas
    Richter.

 6) Use usec resolution for SYN/ACK RTTs in TCP, from Yuchung Cheng.

 7) Support Very High Throughput in wireless MESH code, from Bob
    Copeland.

 8) Allow setting the ageing_time in switchdev/rocker.  From Scott
    Feldman.

 9) Properly autoload L2TP type modules, from Stephen Hemminger.

10) Fix and enable offload features by default in 8139cp driver, from
    David Woodhouse.

11) Support both ipv4 and ipv6 sockets in a single vxlan device, from
    Jiri Benc.

12) Fix CWND limiting of thin streams in TCP, from Bendik Rønning
    Opstad.

13) Fix IPSEC flowcache overflows on large systems, from Steffen
    Klassert.

14) Convert bridging to track VLANs using rhashtable entries rather than
    a bitmap.  From Nikolay Aleksandrov.

15) Make TCP listener handling completely lockless, this is a major
    accomplishment.  Incoming request sockets now live in the
    established hash table just like any other socket too.

    From Eric Dumazet.

15) Provide more bridging attributes to netlink, from Nikolay
    Aleksandrov.

16) Use hash based algorithm for ipv4 multipath routing, this was very
    long overdue.  From Peter Nørlund.

17) Several y2038 cures, mostly avoiding timespec.  From Arnd Bergmann.

18) Allow non-root execution of EBPF programs, from Alexei Starovoitov.

19) Support SO_INCOMING_CPU as setsockopt, from Eric Dumazet.  This
    influences the port binding selection logic used by SO_REUSEPORT.

20) Add ipv6 support to VRF, from David Ahern.

21) Add support for Mellanox Spectrum switch ASIC, from Jiri Pirko.

22) Add rtl8xxxu Realtek wireless driver, from Jes Sorensen.

23) Implement RACK loss recovery in TCP, from Yuchung Cheng.

24) Support multipath routes in MPLS, from Roopa Prabhu.

25) Fix POLLOUT notification for listening sockets in AF_UNIX, from Eric
    Dumazet.

26) Add new QED Qlogic river, from Yuval Mintz, Manish Chopra, and
    Sudarsana Kalluru.

27) Don't fetch timestamps on AF_UNIX sockets, from Hannes Frederic
    Sowa.

28) Support ipv6 geneve tunnels, from John W Linville.

29) Add flood control support to switchdev layer, from Ido Schimmel.

30) Fix CHECKSUM_PARTIAL handling of potentially fragmented frames, from
    Hannes Frederic Sowa.

31) Support persistent maps and progs in bpf, from Daniel Borkmann.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1790 commits)
  sh_eth: use DMA barriers
  switchdev: respect SKIP_EOPNOTSUPP flag in case there is no recursion
  net: sched: kill dead code in sch_choke.c
  irda: Delete an unnecessary check before the function call "irlmp_unregister_service"
  net: dsa: mv88e6xxx: include DSA ports in VLANs
  net: dsa: mv88e6xxx: disable SA learning for DSA and CPU ports
  net/core: fix for_each_netdev_feature
  vlan: Invoke driver vlan hooks only if device is present
  arcnet/com20020: add LEDS_CLASS dependency
  bpf, verifier: annotate verbose printer with __printf
  dp83640: Only wait for timestamps for packets with timestamping enabled.
  ptp: Change ptp_class to a proper bitmask
  dp83640: Prune rx timestamp list before reading from it
  dp83640: Delay scheduled work.
  dp83640: Include hash in timestamp/packet matching
  ipv6: fix tunnel error handling
  net/mlx5e: Fix LSO vlan insertion
  net/mlx5e: Re-eanble client vlan TX acceleration
  net/mlx5e: Return error in case mlx5e_set_features() fails
  net/mlx5e: Don't allow more than max supported channels
  ...

1 files changed, 63 insertions, 19 deletions

diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index e5168f8b9640..5faaa5425f7b 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -38,6 +38,7 @@ struct cls_bpf_prog {
 	struct bpf_prog *filter;
 	struct list_head link;
 	struct tcf_result res;
+	bool exts_integrated;
 	struct tcf_exts exts;
 	u32 handle;
 	union {
@@ -52,6 +53,7 @@ struct cls_bpf_prog {
 
 static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = {
 	[TCA_BPF_CLASSID]	= { .type = NLA_U32 },
+	[TCA_BPF_FLAGS]		= { .type = NLA_U32 },
 	[TCA_BPF_FD]		= { .type = NLA_U32 },
 	[TCA_BPF_NAME]		= { .type = NLA_NUL_STRING, .len = CLS_BPF_NAME_LEN },
 	[TCA_BPF_OPS_LEN]	= { .type = NLA_U16 },
@@ -59,6 +61,20 @@ static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = {
 				    .len = sizeof(struct sock_filter) * BPF_MAXINSNS },
 };
 
+static int cls_bpf_exec_opcode(int code)
+{
+	switch (code) {
+	case TC_ACT_OK:
+	case TC_ACT_SHOT:
+	case TC_ACT_STOLEN:
+	case TC_ACT_REDIRECT:
+	case TC_ACT_UNSPEC:
+		return code;
+	default:
+		return TC_ACT_UNSPEC;
+	}
+}
+
 static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			    struct tcf_result *res)
 {
@@ -79,6 +95,8 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 	list_for_each_entry_rcu(prog, &head->plist, link) {
 		int filter_res;
 
+		qdisc_skb_cb(skb)->tc_classid = prog->res.classid;
+
 		if (at_ingress) {
 			/* It is safe to push/pull even if skb_shared() */
 			__skb_push(skb, skb->mac_len);
@@ -88,6 +106,16 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			filter_res = BPF_PROG_RUN(prog->filter, skb);
 		}
 
+		if (prog->exts_integrated) {
+			res->class = prog->res.class;
+			res->classid = qdisc_skb_cb(skb)->tc_classid;
+
+			ret = cls_bpf_exec_opcode(filter_res);
+			if (ret == TC_ACT_UNSPEC)
+				continue;
+			break;
+		}
+
 		if (filter_res == 0)
 			continue;
 
@@ -195,8 +223,7 @@ static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle)
 	return ret;
 }
 
-static int cls_bpf_prog_from_ops(struct nlattr **tb,
-				 struct cls_bpf_prog *prog, u32 classid)
+static int cls_bpf_prog_from_ops(struct nlattr **tb, struct cls_bpf_prog *prog)
 {
 	struct sock_filter *bpf_ops;
 	struct sock_fprog_kern fprog_tmp;
@@ -230,15 +257,13 @@ static int cls_bpf_prog_from_ops(struct nlattr **tb,
 	prog->bpf_ops = bpf_ops;
 	prog->bpf_num_ops = bpf_num_ops;
 	prog->bpf_name = NULL;
-
 	prog->filter = fp;
-	prog->res.classid = classid;
 
 	return 0;
 }
 
-static int cls_bpf_prog_from_efd(struct nlattr **tb,
-				 struct cls_bpf_prog *prog, u32 classid)
+static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog,
+				 const struct tcf_proto *tp)
 {
 	struct bpf_prog *fp;
 	char *name = NULL;
@@ -268,9 +293,10 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb,
 	prog->bpf_ops = NULL;
 	prog->bpf_fd = bpf_fd;
 	prog->bpf_name = name;
-
 	prog->filter = fp;
-	prog->res.classid = classid;
+
+	if (fp->dst_needed)
+		netif_keep_dst(qdisc_dev(tp->q));
 
 	return 0;
 }
@@ -280,16 +306,13 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
 				   unsigned long base, struct nlattr **tb,
 				   struct nlattr *est, bool ovr)
 {
+	bool is_bpf, is_ebpf, have_exts = false;
 	struct tcf_exts exts;
-	bool is_bpf, is_ebpf;
-	u32 classid;
 	int ret;
 
 	is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS];
 	is_ebpf = tb[TCA_BPF_FD];
-
-	if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf) ||
-	    !tb[TCA_BPF_CLASSID])
+	if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf))
 		return -EINVAL;
 
 	tcf_exts_init(&exts, TCA_BPF_ACT, TCA_BPF_POLICE);
@@ -297,18 +320,32 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp,
 	if (ret < 0)
 		return ret;
 
-	classid = nla_get_u32(tb[TCA_BPF_CLASSID]);
+	if (tb[TCA_BPF_FLAGS]) {
+		u32 bpf_flags = nla_get_u32(tb[TCA_BPF_FLAGS]);
+
+		if (bpf_flags & ~TCA_BPF_FLAG_ACT_DIRECT) {
+			tcf_exts_destroy(&exts);
+			return -EINVAL;
+		}
+
+		have_exts = bpf_flags & TCA_BPF_FLAG_ACT_DIRECT;
+	}
+
+	prog->exts_integrated = have_exts;
 
-	ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog, classid) :
-		       cls_bpf_prog_from_efd(tb, prog, classid);
+	ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) :
+		       cls_bpf_prog_from_efd(tb, prog, tp);
 	if (ret < 0) {
 		tcf_exts_destroy(&exts);
 		return ret;
 	}
 
-	tcf_bind_filter(tp, &prog->res, base);
-	tcf_exts_change(tp, &prog->exts, &exts);
+	if (tb[TCA_BPF_CLASSID]) {
+		prog->res.classid = nla_get_u32(tb[TCA_BPF_CLASSID]);
+		tcf_bind_filter(tp, &prog->res, base);
+	}
 
+	tcf_exts_change(tp, &prog->exts, &exts);
 	return 0;
 }
 
@@ -429,6 +466,7 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 {
 	struct cls_bpf_prog *prog = (struct cls_bpf_prog *) fh;
 	struct nlattr *nest;
+	u32 bpf_flags = 0;
 	int ret;
 
 	if (prog == NULL)
@@ -440,7 +478,8 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 	if (nest == NULL)
 		goto nla_put_failure;
 
-	if (nla_put_u32(skb, TCA_BPF_CLASSID, prog->res.classid))
+	if (prog->res.classid &&
+	    nla_put_u32(skb, TCA_BPF_CLASSID, prog->res.classid))
 		goto nla_put_failure;
 
 	if (cls_bpf_is_ebpf(prog))
@@ -453,6 +492,11 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 	if (tcf_exts_dump(skb, &prog->exts) < 0)
 		goto nla_put_failure;
 
+	if (prog->exts_integrated)
+		bpf_flags |= TCA_BPF_FLAG_ACT_DIRECT;
+	if (bpf_flags && nla_put_u32(skb, TCA_BPF_FLAGS, bpf_flags))
+		goto nla_put_failure;
+
 	nla_nest_end(skb, nest);
 
 	if (tcf_exts_dump_stats(skb, &prog->exts) < 0)